Complexity Prediction on HotpotQA
86.3ROC-AUCIntroLM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| IntroLMBackbone Model=Qwen3-8B2026.01 | 86.3 | 46.7 | |
| DeBERTa-v3-LargeNumber of Parameters=435M, Backbone Model=DeBERTa-v3-Large2026.01 | 71.8 | 26.8 | |
| DeBERTa-v3-BaseNumber of Parameters=184M, Backbone Model=DeBERTa-v3-Base2026.01 | 69.4 | 24.3 |